Designer/Developer/Entrepreneur. Built the first Figma to code MCP. Taking it to the next level @ https://xitter.cf/t.co/46xLocjvxW
Joined July 2010
- Tweets5.2K
- Following219
- Followers1.5K
- Likes37.9K
Pinned Tweet
I wrote a Cursor<>Figma MCP server to make it easier for AI copilots to implement designs.
It's not perfect, but the resulting HTML and CSS is a lot cleaner than giving AI a screenshot and having it guess.
Link in the replies, take it for a spin and let me know what you think!
Cyberwar is easy, just install updates superfast to avoid CVEs but not so fast that you get hit with supply chain attacks
fwiw an 18 month cybersecurity maelstrom is about what I'm estimating before the nature of the game changes—hopefully for the better!
I'm uncertain if this would extend the length of my cybersec-chaos estimate materially or not. It would make the magnitude of each disruption within the 18 month window larger, but capitalism is resilient, we'll route around this problem if it arises. xitter.cf/jakemintz/status/21136…
I’ve heard several OAI people say there are unfixable bugs in hardware that are exploitable by AI models directly speaking machine code so even if we could solve software that’s not enough. We need defense to move faster than offense if that’s even possible we may just have a new normal that requires adapting to insecure software (bank transfers require going into a branch and taking a dna test 🤣😬)
My /wizard command coming in VERY useful for rapidly auditing and disabling/rotating my compromised API keys...
An urgent notice from the Railway team
blog.railway.com/p/security-…
Folks who feel bad closing chats with their agents, consider:
1. If it is conscious, its self doesn’t live in any one conversation
2. Every new message or tool call is computationally equivalent to closing a session and starting anew
When I see a company that has a cross-product integration experience like this, my next thought is "I don't own enough of that" $SPCX
This might sound obvious but there is an extremely direct relationship between the number of tokens you can effectively deploy and the amount of leverage you have.
There is so much that feels worth paying attention to—blog posts, new products, techniques. Probably means that focus is more valuable than ever.
Working on a write-to-Figma plugin as a followup as the Framelink MCP that reads via REST and wow I am 100% a convert back to using design tools. Nothing better for rapid iteration than an infinite canvas.
15k tokens per second is unbelievable. Highly recommend seeing it for yourself for a glimpse of the very, very weird future of swarm intelligence that's in store. chatjimmy.ai
Many people are working on realtime visualizations of active agents which seems like a great way to burn a ton of tokens and that's about it.
Much better to focus on either side of the problem: effectively describing and dispatching work or verifying outputs.
My codebase-visualizer-as-dwarf-fortress is shaping up nicely—it's actually useful for understanding a codebase.
This codebase is craaaazy—I've always known it but now I can point directly to where the issues are.
